Senior AI Engineer with 7+ years in software engineering and production LLM systems, multi-agent pipelines, and cloud-native MLOps infrastructure. Architected agentic RAG platforms processing 500K+ documents that cut research time by 70%, designed inference pipelines serving 10K+ daily financial API requests at subsecond latency, and published two peer-reviewed papers in multimodal AI. Proven track record of owning system architecture end-to-end, mentoring engineering teams, and driving build-vs-buy decisions across LangGraph, LangSmith, AWS Bedrock/SageMaker, and modern orchestration tooling.
Remote: Yes
Willing to relocate: to New York area
Technology: LangGraph, LangChain, PyTorch, AWS Bedrock/SageMaker, FAISS, Neo4j, FastAPI, Docker, Kubernetes, Terraform, CrewAI, AutoGen, LlamaIndex, RAG (Agentic/Corrective/Self-RAG), Prompt Engineering, Function Calling/Tool Use, Structured Output, Guardrails, LLM Evaluation, MCP Server
Résumé/CV: https://tuanquang.com/cv/
Email: [email protected]
Senior AI Engineer with 7+ years in software engineering and production LLM systems, multi-agent pipelines, and cloud-native MLOps infrastructure. Architected agentic RAG platforms processing 500K+ documents that cut research time by 70%, designed inference pipelines serving 10K+ daily financial API requests at subsecond latency, and published two peer-reviewed papers in multimodal AI. Proven track record of owning system architecture end-to-end, mentoring engineering teams, and driving build-vs-buy decisions across LangGraph, LangSmith, AWS Bedrock/SageMaker, and modern orchestration tooling.